Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    component and library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calories
    0.50
     consonants
    0.48
     metabolites
    0.47
     pièce
    0.46
     nihil
    0.46
     pièces
    0.46
     muscles
    0.45
     trousers
    0.45
     キー
    0.45
     discordant
    0.45
    POSITIVE LOGITS
    들과
    0.60
    maker
    0.58
    ation
    0.57
    들을
    0.56
    ಗಳನ್ನು
    0.55
    们
    0.54
    lets
    0.54
    体系
    0.54
    들의
    0.53
    m
    0.52
    Act Density 0.123%

    No Known Activations